© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30504
    Prev
    Next
    INDEX
    Explanations

    numerical values and proportions in context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ant
    -0.45
     hår
    -0.44
    thong
    -0.39
     jura
    -0.38
    deltaTime
    -0.38
     
    -0.37
    uno
    -0.37
    OGEN
    -0.37
    ell
    -0.36
    est
    -0.36
    POSITIVE LOGITS
    SharedCtor
    1.12
     Roskov
    1.12
    featureID
    1.08
    RenderAtEndOf
    1.07
     resourceCulture
    1.03
    Geplaatst
    1.02
    
    1.00
     '\\;'
    0.99
     ModelExpression
    0.98
     Италијани
    0.96
    Activations Density 0.080%

    No Known Activations